FinOps skills

CloudQuell ships a set of FinOps skills — packaged workflow runbooks in the open Agent Skills format — that teach your AI agent how to run proven FinOps workflows on top of the CloudQuell MCP server. Install a skill once and your agent knows the whole routine: which CloudQuell tools to call with which parameters, what to double-check, when to stop and ask you, and how to present the result.

Skills are instructions, not access. They only work once the CloudQuell connector is set up, and they never bypass CloudQuell’s gates: tool calls require a paid plan, and changes are off by default for every organization — an org admin has to enable them in Settings → Organization → AI agent access, the caller must hold an admin role, and every write still needs per-call confirmation. The skills themselves instruct the agent to get your explicit approval before any write, and to report the reason and carry on read-only when a write is refused.

The skills

Skill	What your agent learns	Writes?
Weekly briefing	Start here. One get_finops_briefing call answers “what should I look at today?” — data freshness first, then the month-end forecast, top movers, anomalies, budgets at risk, expiring commitments and open savings. The agent then drills into only the sections that cross a threshold, using the tool named for each. Built for a Monday-morning review or an unattended daily run.	No
Spend review	Monthly/weekly cost review: ranks the movers with compare_periods, projects month-end with get_forecast, then breaks the total down by usage type or tag with run_cost_pivot. Covers direct AI-provider spend too.	No
Anomaly triage	Detect unusual spend, investigate to the resource level with get_resource_breakdown, and pivot by region / usage family / charge type when no single resource explains the jump. Dismiss noise with an audit trail or escalate real spikes.	Dismissals only
Budget guardrails	Budget health & forecast checks, coverage audit, creating/tuning budgets, wiring and testing notification channels	Yes
Savings actions	Prioritize savings recommendations by value/effort/confidence, track them to banked savings, plan RI/Savings Plan renewals	Status updates
Allocation hygiene	Tag-coverage and cost-center audit, then run_cost_pivot by cost_center and by tag:<key> to show what each centre actually spends on and where the untagged dollars sit — ending in a ranked remediation plan	No

Each skill is a folder containing a SKILL.md runbook, validated against the live tool surface. The read-only skills give full value on a read-only connection — which is every connection until an admin turns changes on — and the writing skills degrade gracefully to analysis + proposals when they are refused.

Download

Last built from CloudQuell MCP server 0.4.0. The runbooks are validated against that tool surface — if you connected earlier, re-download to pick up the new weekly briefing skill and the changes-off-by-default guidance.

• All six skills (bundle): cloudquell-finops-skills.zip
• Individual skills: weekly-briefing · spend-review · anomaly-triage · budget-guardrails · savings-actions · allocation-hygiene

Skills are also served as MCP prompts

You do not have to install anything to get these workflows. The CloudQuell MCP server also serves all six as MCP prompts, so any client that supports the prompt list gets them straight from the connection — same runbooks, nothing to download, and they update when the server does.

In a client that surfaces prompts (Claude Desktop’s prompt picker, for example) they appear as cloudquell-weekly-briefing, cloudquell-spend-review, cloudquell-anomaly-triage, cloudquell-budget-guardrails, cloudquell-savings-actions and cloudquell-allocation-hygiene.

The downloadable Agent Skills below are for clients that support Agent Skills but not MCP prompts — Claude Code being the common case. Use whichever your client supports; installing both is harmless but redundant.

Install

Claude Code

Unzip the bundle into your project’s .claude/skills/ (shared with your team via the repo) or ~/.claude/skills/ (personal, all projects):

curl -sL https://docs.cloudquell.com/downloads/skills/cloudquell-finops-skills.zip -o /tmp/cq-skills.zip
unzip /tmp/cq-skills.zip -d ~/.claude/skills/

Add the connector if you haven’t:

claude mcp add --transport http cloudquell https://mcp.cloudquell.com/mcp

Claude picks the right skill automatically when a request matches — “why did our AWS bill spike?” engages anomaly triage — or invoke one explicitly, e.g. /cloudquell-spend-review.

Claude.ai / Claude Desktop

1. Add the CloudQuell connector: Settings → Connectors → Add custom connector with URL https://mcp.cloudquell.com/mcp (details in Connecting).
2. Upload skills under Settings → Capabilities → Skills, one individual skill zip at a time (the uploader expects one skill per zip).
3. In a chat, ask a matching question — the skill engages on its own.

Other agents

Any agent that supports the Agent Skills format can use these: unzip and point the agent at the skill folders. The tool names referenced in each SKILL.md are the CloudQuell MCP tool names as served by the endpoint, so they work regardless of any client-side prefixing.

What a skill run looks like

Asking “are we on budget this month?” with the budget-guardrails skill installed: the agent calls get_budget_status, leads with anything over or forecast-breaching, audits coverage against your actual top spend via query_costs, and comes back with a status table plus proposed changes — each with exact parameters — waiting for your go-ahead before creating or modifying anything.

Good to know

• Skills complement — not replace — the example prompts & workflows: the examples show what’s possible in one-off questions; skills make the full routine repeatable and consistent.
• Skills are versioned with the MCP tool surface. If a tool gains parameters or a new tool ships, updated skill zips land here — reinstalling is just replacing the folder. See the Changelog.
• On the Free plan the connector works but every tool call returns upgrade_required — the skills detect this and explain rather than fail cryptically. See Access, limits & data scope.